Agent Skills and WebMCP

Machine-readable LLMBase skills, read-only WebMCP tools, and content negotiation support.

Updated May 11, 2026

LLMBase publishes read-only agent metadata for tools that can discover website capabilities automatically. These resources are separate from chat-agent API authentication. Use Agent integrations when you want OpenClaw, Hermes, or another OpenAI-compatible agent to consume a Pro or Business chat subscription.

Agent Skills

LLMBase hosts first-party skill artifacts directly on the website so agents can verify them with the SHA-256 digests from the discovery index.

Current skills:

llmbase-api
llmbase-chat-agent
llmbase-model-discovery
llmbase-mcp

The discovery index is available at:

/.well-known/agent-skills/index.json

WebMCP

On public pages, LLMBase registers a small set of read-only WebMCP tools for:

public model search
public leaderboard queries
docs lookup
pricing page lookup

These tools are only registered when the browser exposes a supported WebMCP API surface. Unsupported browsers continue to work normally.

Markdown responses

Public pages can negotiate a machine-readable Markdown response when the client sends a compatible Accept header. Check the response Content-Type; clients must continue to support HTML when a Markdown representation is unavailable.